基于知识决策树的城市水体提取方法研究.pdfVIP

第 28 卷第 1 期 遥感信息 Vo l. 28 ,No.l 2013 年 2 月 Remote Sensing Information Feb. ,2013 基于知识决策树的城市水体提取方法研究 陈静波①，刘顺喜②，汪承义①，尤淑撑②，王忠武② 〈①中国科学院遥感应用研究所，北京 100101 ，②中国土地勘测规划院，北京 100035) 摘要:针对城市水体与建筑物阴影、洒青路面和浓密植被等暗地物的光谱混淆性，构建了结合光谱特征和空 间特征的城市水体提取知识决策树。其基本思路为 z 首先利用短波红外波段提取暗地物，其次分别利用浓密植被 在近红外波段和洒青路面在红波段中的反射率剔除这两类暗地物，再次利用空间密度特征剔除建筑物阴影，最后 根据面积对水体进行补充识剔。与现有方法相比，本方法提出了城市水体提取中需关注的暗地物类型并开展针 对性特征分析，并利用由噪声环境下密度聚类方法(DBSCAN)描述的空间密度特征区分城市水体和建筑物阴影。 对北京城区 SPOT 5 多光谱影像开展的实验得到的检测率为 86.18% ，虚警率为 13.82% ，表明本方法是基于中分 辨率多光谱影像提取城市水体的有效方法。 关键词:城市水体z 知识决策树;建筑物阴影z 暗地物;空间密度;DBSCAN dOÌ: 10. 3969 /j. issn. 1000-3177.2013.01. 007 中固分类号:TP751 文献标识码:A 文章编号:1000→3177(2013)125一0029 一05 Research on Urban Water Body Extraction Using Knowledge-based Decision Tree CHEN Jing-bo(,LIU Shun-xi(%} • WANG Cheng-y严.YOU Shu-cheng(%} ,WANG Zhong-wu② <( Institute of Remote Sensing Applications ,Chinese Academy of Sciences ,Beijing 100101 , ( China Land Sur四ying and Planning Institute ,Beijing 100035) Abstr辄t: In view of the spectral mixing between water body. building shadow ,asphalt road and dense vegetation in urban environment ,a knowledge-based decision tree combining spectral and spatial features is constructed to extract water body the- matic information in this paper. Firstly ,dark objects in urban environment are extracted using threshold of reflect且nce in SWIR. Secondly ,dense vegetation and asphalt road are eliminated according to their reflectance in NIR and R respectively. Thirdly , differences in spatial density are used to eliminate building shadow. Finally ,area threshold is used for supplementary recognition